Search

Smart body area networks (SmartBAN) is an emerging wireless body area networks (WBAN) standard proposed by the European Telecommunications Standards Institute (ETSI). This paper first examines the potential of SmartBAN medium access control (MAC) layer with scheduled access to support a myriad of WBAN applications, having diverse data rate requirements. Extra scheduled access slots can be allocated to high date rate sensor nodes for managing their data rate requirements. High data rate sensor nodes can also be re-assigned to use the available time slots of low data rate sensor nodes in Inter-Beacon Interval (IBI) by the central hub. But these two schemes incorporate different physical (PHY) and MAC layer overheads related to frame transmission, frame acknowledgement and slot re-assignment. This redundant overhead transmission results in high overhead energy consumption and reduced effective throughput. Therefore, an innovative and flexible enhanced throughput and reduced overhead (FETRO) MAC protocol for scheduled access is proposed in this article. In the proposed scheme, the sensor node data rate requirements are considered while assigning the scheduled access slot duration by allowing minimal changes in the base-line standard implementation. This infers the provision of scheduled access slots with variable slot durations within an IBI. We also evaluate the existing techniques of extra slot allocation and slot re-assignment in SmartBAN as well as the proposed FETRO MAC protocol with variable slot length. The proposed FETRO MAC scheme results in optimizing both the overall throughput and normalized overhead energy consumption per kilo bits per second (Kbps). Additionally, the impact of various WBAN channel models over these throughput management approaches is also investigated. The proposed FETRO MAC protocol with variable slot duration gives an average reduction of 65.5% and 59.16%, respectively, in the hub and nodes normalized overhead energy consumption per Kbps outcomes, as compared to the de-facto SmartBAN MAC scheduling strategies.

Vehicle platoon, a novel vehicle driving paradigm that organizes a group of vehicles in the nose-to-tail structure, has been considered as a potential solution to reduce traffic congestion and increase travel comfort. In such a platoon system, head vehicles' performances are usually evaluated by user vehicles' feedbacks. Selection of an appropriate and reliable head vehicle while not disclosing user vehicles' privacy has become an interesting problem. In this article, we present a trust-based and privacy-preserving platoon recommendation scheme, called TPPR, to enable potential user vehicles avoid selecting the malicious head vehicles. The basic concept of TPPR is that each user vehicle holds a trust value, and the reputation score of the head vehicle is calculated via a truth discovery process. To preserve vehicles' privacy, pseudonyms and Paillier cryptosystem are applied. In addition, novel authentication protocols are designed to ensure that only the valid vehicles (i.e., the vehicles holding the truthful trust values and joining the vehicle platoon) can pass the authentication. A comprehensive security analysis is conducted to prove that the proposed TPPR scheme is secure against several sophisticated attacks in vehicular ad hoc networks. Moreover, extensive simulations are conducted to demonstrate the correctness and effectiveness of the proposed scheme.

Distributed learning algorithms aim to leverage distributed and diverse data stored at users' devices to learn a global phenomena by performing training amongst participating devices and periodically aggregating their local models' parameters into a global model. Federated learning is a promising paradigm that allows for extending local training among the participant devices before aggregating the parameters, offering better communication efficiency. However, in the cases where the participants' data are strongly skewed (i.e., non-IID), the local models can overfit local data, leading to low performing global model. In this paper, we first show that a major cause of the performance drop is the weighted distance between the distribution over classes on users' devices and the global distribution. Then, to face this challenge, we leverage the edge computing paradigm to design a hierarchical learning system that performs Federated Gradient Descent on the user-edge layer and Federated Averaging on the edge-cloud layer. In this hierarchical architecture, we formalize and optimize this user-edge assignment problem such that edge-level data distributions turn to be similar (i.e., close to IID), which enhances the Federated Averaging performance. Our experiments on multiple real-world datasets show that the proposed optimized assignment is tractable and leads to faster convergence of models towards a better accuracy value. 2013 IEEE. Scopus

The Internet of Things (IoT) is experiencing explosive growth and has gained extensive attention from academia and industry in recent years. However, most of the existing IoT infrastructures are centralized, which may cause the issues of unscalability and single-point-of-failure. Consequently, decentralized IoT has been proposed by taking advantage of the emerging technology called blockchain. Voting systems are widely adopted in IoT, for example a leader election in wireless sensor networks. Self-tallying voting systems are alternatives to unsuitable, traditional centralized voting systems in decentralized IoT. Unfortunately, self-tallying voting systems inherently suffer from fairness issues, such as adaptive and abortive issues caused by malicious voters. To address these issues, in this paper, we introduce a framework of the self-tallying voting system in decentralized IoT based on blockchain. We propose a concrete construction and prove that the proposed system satisfies all the security requirements, including fairness, dispute-freeness and maximal ballot secrecy. We simulate the algorithms on a laptop, an Android phone and a Raspberry Pi to test the time consumption and evaluate the gas cost of each algorithm in a private blockchain as well. The implementation results demonstrate the practicability of our system

Since the emergence of digital and smart healthcare, the world has hastened to apply various technologies in this field to promote better health operation and patients’ well being, increase life expectancy, and reduce healthcare costs. One promising technology and game changer in this domain is digital twin (DT). DT is expected to change the concept of digital healthcare and take this field to another level that has never been seen before. DT is a virtual replica of a physical asset that reflects the current status through real-time transformed data. This article proposes and implements an intelligent context-aware healthcare system using the DT framework. This framework is a beneficial contribution to digital healthcare and to improve healthcare operations. Accordingly, an electrocardiogram (ECG) heart rhythms classifier model was built using machine learning to diagnose heart disease and detect heart problems. The implemented models successfully predicted a particular heart condition with high accuracy in different algorithms. The collected results have shown that integrating DT with the healthcare field would improve healthcare processes by bringing patients and healthcare professionals together in an intelligent, comprehensive, and scalable health ecosystem. Also, implementing an ECG classifier that detects heart conditions gives the inspiration for applying ML and artificial intelligence with different human body metrics for continuous monitoring and abnormalities detection. Finally, neural-network-based algorithms deal better with ECG data than traditional ML algorithms.

Air pollution monitoring, finding the hazardous zone, and future air quality predictions have recently become a significant issue for many researchers. With the adverse effect of low air quality on human health, it has become necessary for predicting the air quality index (AQI) accurately and on time. The unmanned aerial vehicle (UAV) can collect air quality data with high spatial and temporal resolutions. Using a fleet of UAVs could be considered a good option. In the proposed work, we implement a distributed federated learning (FL) algorithm within a UAV swarm that collects air quality data using built-in sensors. A scheme for finding the area with the highest AQI value is proposed using swarm intelligence. The collected data are then fed to a CNN-LSTM model to predict the AQI. The trained local model is sent to the central server, and the server aggregates the received models from UAVs in the swarm. A global model is created and is transmitted to the UAV swarm again in the next iteration. The proposed architecture is compared with other time-series models. The results show that the proposed model predicts AQI daily with a minimal error rate on a real-time data set from Delhi.

At present, computed tomography (CT) is widely used to assist disease diagnosis. Especially, computer aided diagnosis (CAD) based on artificial intelligence (AI) recently exhibits its importance in intelligent healthcare. However, it is a great challenge to establish an adequate labeled dataset for CT analysis assistance, due to the privacy and security issues. Therefore, this paper proposes a convolutional autoencoder deep learning framework to support unsupervised image features learning for lung nodule through unlabeled data, which only needs a small amount of labeled data for efficient feature learning. Through comprehensive experiments, it shows that the proposed scheme is superior to other approaches, which effectively solves the intrinsic labor-intensive problem during artificial image labeling. Moreover, it verifies that the proposed convolutional autoencoder approach can be extended for similarity measurement of lung nodules images. Especially, the features extracted through unsupervised learning are also applicable in other related scenarios.

HDFS faces several issues when it comes to handling a large number of small files. These issues are well addressed by archive systems, which combine small files into larger ones. They use index files to hold relevant information for retrieving a small file content from the big archive file. However, existing archive-based solutions require significant overheads when retrieving a file content since additional processing and I/Os are needed to acquire the retrieval information before accessing the actual file content, therefore, deteriorating the access efficiency. This paper presents a new archive file named Hadoop Perfect File (HPF). HPF minimizes access overheads by directly accessing metadata from the part of the index file containing the information. It consequently reduces the additional processing and I/Os needed and improves the access efficiency from archive files. Our index system uses two hash functions. Metadata records are distributed across index files using a dynamic hash function. We further build an order-preserving perfect hash function that memorizes the position of a small file's metadata record within the index file.

The smart grid emerges as a new era of the electronic power grid. It integrates advanced sensing technologies, communications, and controlling methods that tell how electricity travels from different generation points to consumers. In order to fulfill customers’ satisfaction and two way communications, a huge number of smart meters are deployed in different countries for real-time consumption and presentation of the rigorous energy usage. The privacy of industrial ecosystems may require greater attention while considering minimum network load, lower computational resources, better energy efficiency, and accuracy of data. Different research works have been done to tackle customers’ privacy, but at the cost of using more computational resources, communication overhead, and hiring of a trusting third party. In this article, we have proposed a symmetric encryption scheme for industrial ecosystems in the Internet of Thing (IoT) environment. The performance evaluation and security analysis demonstrate successful user privacy and integrity with lower computational resources and communication overhead.

In softwarized industrial networking, honeypot identification is very important for both the attacker and the defender. Existing honeypot identification relies on simple features of honeypot. There exist two challenges: The simple feature is easily simulated, which causes inaccurate results, whereas the advanced feature relies on high interactions, which lead to security risks. To cope with these challenges, in this article, we propose a secure fuzzy testing approach for honeypot identification inspired by vulnerability mining. It utilizes error handling to distinguish honeypots and real devices. Specifically, we adopt a novel identification architecture with two steps. First, a multiobject fuzzy testing is proposed. It adopts mutation rules and security rules to generate effective and secure probe packets. Then, these probe packets are used for scanning and identification. Experiments show that the fuzzy testing is effective and corresponding probe packet can acquire more features than other packets. These features are helpful for honeypot identification.

With the development of the industrial Internet of Things and the advancements in wireless sensor networking technologies, the smart grid based on edge computing now is regarded as being essential for real-time monitoring and automatic control of the electricity generation and distribution. In this article, we propose a highly efficient energy control framework supported by edge computing to reduce energy waste and increase the benefit for industrial users. To this end, battery energy storage systems (BESSs) are currently being employed to store energy for stability of supply and quality of power. The optimal load patterns and corresponding energy storage capacities of the BESSs can be obtained through the framework, according to the energy market and the historical load data of industrial users. However, computing these requires considering the tradeoff between equipment cost, time-of-use electricity price, running expenses, and other related factors, which would be an NP-hard problem. To address this challenge, we also propose an adaptive mixed differential evolution algorithm with a novel mutation strategy. Experiments on real-world data demonstrate the effectiveness of the proposed algorithm and framework.

Advanced persistent threat (APT), with intense penetration, long duration, and high customization, has become one of the most grievous threats to cybersecurity. Furthermore, the design and development of Internet-of-Things (IoT) devices often do not focus on security, leading APT to extend to IoT, such as the Internet of emerging unmanned aerial vehicles (UAVs). Whether malware with attack payload can be successfully implanted into UAVs or not is the key to APT on the Internet of UAVs. APT malware on UAVs establishes communication with the command and control (C&C) server to achieve remote control for UAVs-aware information stealing. Existing effective methods detect malware by analyzing malicious behaviors generated during C&C communication. However, APT malware usually adopts a low-traffic attack mode, a large amount of normal traffic is mixed in each attack step, to avoid virus checking and killing. Therefore, it is difficult for traditional malware detection methods to discover APT malware on UAVs that carry weak abnormal signals. Fortunately, we found that most APT attacks use domain name system (DNS) to locate C&C server of malware for information transmission periodically. This behavior will leave some records in the network flow and DNS logs, which provides us with an opportunity to identify infected internal UAVs and external malicious domain names. This article proposes an APT malware on the Internet of UAVs detection method combining string matching and Fourier transformation based on DNS traffic, which is able to handle encrypted and obfuscated traffic due to packet payloads independence. We preprocessed the collected network traffic by converting DNS timestamps of DNS request to strings and used the trained random forest model to discover APT malware domain names based on features extracted through string-matching-based periodicity detection and Fourier transformation-based periodicity detection. The proposed method has been evaluated on the data set, including part of normal domains from the normal traffic and malicious domains marked by security experts from APT malware traffic. Experimental results have shown that our proposed detection method can achieve the accuracy of 94%, which is better than the periodicity detection algorithm alone. Moreover, the proposed method does not need to set the confidence to filter the periodicity with high confidence.

To satisfy future wireless network’s requirements of huge capacity, ultra low delay and supermassive connectivity, it is urgent to study novel wireless communication network architecture and technology. Fog-computing radio access network (F-RAN) is a newly developed network paradigm, in which the edge devices perform the storage, communication, control, configuration and management. Meanwhile, non-orthogonal multiple access (NOMA) has been considered to be a hopeful multiple access mechanism for future radio access networks (RANs). The distinctive feature of NOMA is to assign the same channel for various users simultaneously by utilizing the power domain. With the deployment of NOMA, F-RAN can further promote system throughput, time latency, access capability and spectrum efficiency. The coordination between NOMA and F-RAN provides powerful support to extensive application of augmented/virtual reality (AR/VR), vehicular networking, intelligent medical and other emerging applications. In this paper, we focus on a noncooperative game resource optimization to decrease the complexity while the dynamic optimization problem is decoupled to subchannel assignment and power allocation. Matching theory is applied to propose a subchannel assignment scheme. Then, we convert and decouple the power allocation problem into three subproblems and solve them separately at each slot. Simulation results illustrate the potency of the proposed noncooperative resource allocation scheme.

Nowadays, the advance of smart grid technology has fostered the development of microgrids, which can efficiently control and manage the distributed energy resources (DERs). In smart grid, IoT devices generate huge amounts of data, which are collected and shared among DERs, microgrids, and the main grid. To protect the shared data, it is necessary to implement the secure and efficient data access control. Ciphertext policy attribute-based encryption (CP-ABE) is a promising solution for the distributed system. However, lightweight IoT devices with limited computing capability cannot handle the computationally intensive ABE algorithms. To overcome this constraint, the decryption phase of CP-ABE is usually outsourced to the cloud, but this is inefficient and not safe enough in the distributed environment. In this article, we propose an edge blockchain empowered secure data access control scheme with fair accountability for the smart grid. The computation workloads of end user devices are outsourced to the edge nodes in a consortium blockchain system We adopt an on-chain/off-chain approach to ensure the flexible data sharing. Additionally, we adopt the threshold secret sharing scheme to establish a distributed authority. The security analysis and performance evaluation are conducted to prove the security and efficiency of our scheme. We use the Raspberry Pi to simulate lightweight IoT devices in the Hyperledger fabric platform to prove the usability of our scheme.

Mobile-edge computing (MEC) has emerged as a new computing paradigm with great potential to alleviate resource limitations attributed to mobile device users (MDUs) by offloading intensive computations to ubiquitous MEC server. However, most of the current offloading policies allow MDUs to transmit their tasks to the same connected small base stations (sBSs), which invariably increases latency and limits performance gain due to overload. Moreover, the security issue mitigating sensitive communication of information is not adequately addressed. Therefore, in this study, in addition to proposing a joint load balancing and computation offloading (CO) technique for MEC systems, we introduce a new security layer to circumvent potential security issues. First, a load balancing algorithm for efficient redistribution of MDUs among sBSs is proposed. In addition, a new advanced encryption standard (AES) cryptographic technique suffused with electrocardiogram (ECG) signal-based encryption and decryption key is presented as a security layer to safeguard the vulnerability of data during the transmission. Furthermore, an integrated model of load balancing, CO and security is formulated as a problem whose goal is to decrease the time and energy demands of the system. Detailed experimental results prove that our model with and without the additional security layers can save about 68.2% and 72.4% of system consumption compared to the local execution.

Online banks may disclose consumers’ shopping preferences due to various attacks. With differential privacy, each consumer can disturb his consumption amount locally before sending it to online banks. However, directly applying differential privacy in online banks will incur problems in reality because existing differential privacy schemes do not consider handling the noise boundary problem. In this paper, we propose an Optimized Differential prIvate Online tRansaction scheme (O-DIOR) for online banks to set boundaries of consumption amounts with added noises. We then revise O-DIOR to design a RO-DIOR scheme to select different boundaries while satisfying the differential privacy definition. Moreover, we provide in-depth theoretical analysis to prove that our schemes are capable to satisfy the differential privacy constraint. Finally, to evaluate the effectiveness, we have implemented our schemes in mobile payment experiments. Experimental results illustrate that the relevance between the consumption amount and online bank amount is reduced significantly, and the privacy losses are less than 0.5 in terms of mutual information.

5G and beyond (B5G) networks are leading a digital revolution in telecommunication in both academia and industry. It brings new paradigms in many aspects of people's daily lives due to its advantages. However, it still leaves some issues in terms of security and privacy as challenges. Blockchain, the public database, is an alternative to the traditional centralized systems, serving as the backbone technique in many systems, including manufacturing, economics, and industry. Blockchain is promising in solving the security issues in the sense that it provides desirable properties including decentralization, transparency, immutability, and so on. In this article, we investigate typical security and privacy issues in edge intelligence in B5G networks and devise a framework to integrate blockchain with such systems, which can provide guaranteed security as well as privacy. We also illustrate several possible solutions to these security and privacy issues in edge intelligence in B5G systems based on blockchain and Ethereum to show how blockchain contributes to the coming B5G networks. This work is supported by the National Natural Science Foundation of China under Grant 61872229 and Grant U19B2021, the Key Research and Development Program of Shaanxi under Program 2020ZDLGY09-06, and the Block-chain Core Technology Strategic Research Program of the Ministry of Education of China under Grant 2020KJ01030, and Hongkong Macao Joint Research Grant 2019WGALH21.. Yong Yu is the corresponding author.

Next-generation communication networks can provide high capacity, low latency, and massive connections; however, they introduce novel challenges of management complexity, and traditional mathematical methods cannot well characterize the rational behavior of users. In this article, we pay attention to the methods of artificial intelligence (AI) and game theory. We first review the applications of machine learning (ML) and game theory models in wireless communications and summarize their advantages and disadvantages. After surveying the state of the art, in this article we propose a novel framework combining ML and game theory, which explores and exploits the benefits of the two disciplines. Finally, we apply our novel framework to solve the network selection problem in a 5G ultra-dense and heterogeneous network. Simulation results confirm the advantage of our presented framework on reducing the average delay of users.

The data in industrial informatics may be high-dimensional and mislabeled. Irrelevant or noisy features pose a significant challenge to the detection of high-dimensional mislabeling. The traditional method usually adopts a two-step solution, first finding the relevant subspace and then using it for mislabeling detection. This two-step method struggles to provide the optimal mislabeling detection performance, since it separates the procedures of feature selection and label error detection. To solve this problem, in this article, we integrate the two steps and propose a sequential ensemble noise filter (SENF). In the SENF, relevant features are selected and used to generate a noise score for each instance. Continuously, these noise scores guide feature selection in the regression learning. Thus, the SENF falls in the scope of sequential ensemble learning. We evaluate our approach on several benchmark datasets with high dimensionality and much label noise. It is shown that the SENF is significantly better than other existing label noise detection methods. This work was supported in part by the National Key Research, and Development Program under Grant 2017YFE0125300 and Grant 2018YFB1702700, in part by the National Natural Science Foundation of China under Grant 61672284 and Grant 61772233, in part by the Key Research and Development Program of Jiangsu Province under Grant BE2019012 and Grant BE2019648, and in part by the project of Shenzhen Science and Technology Innovation Committee under Grant JCYJ20190809145407809.

With the widespread use of online social networks, billions of pieces of information are generated every day. How to detect new topics quickly and accurately at such data scale plays a vital role in information recommendation and public opinion control. One of the basic research tasks of topic detection is how to represent a topic. The existing topic representation models do not focus on how to select better differentiated words to represent topics, are still computer-centered, and do not effectively combine human intelligence and artificial intelligence (AI). To solve these problems, this article proposes a word-distributed sensitive topic representation model (WDS-LDA) based on hybrid human-AI (H-AI). The basic idea is that the distribution of words within a topic or among different topics has a great influence on the selection of topic expression words. If a word is evenly distributed among all documents of a certain topic, it indicates that the word is the common word of all documents in the topic, and it is more suitable to represent this topic. If a word is more evenly distributed among various topics, it indicates that the word is a common word of all topics, and cannot be used for the purpose of distinguishing among topics, becoming less suitable to represent any topic. At the same time, the human cognitive ability and cognitive models are introduced into topic representation based on H-AI. We introduce the user's modification of topic expression words into the topic model representation so that the topic model can learn human wisdom and become more and more accurate. Therefore, three different weights are introduced: inside weight; outside weight; and manual adjustment weight. The inside weight describes the uniform distribution of a word in the given topic, the outside weight describes the uniform distribution of a word in all topics, and the manual adjustment weight reflects whether a word is suitable as a representative vocabulary in the past manual adjustment. Tests using Sina microblog's actual data sets show that the WDS-LDA algorithm makes the representative words more important, the distinction among different topic words higher, and effectively improves the precision of subsequent algorithms, such as topic detection and topic evolutionary analysis using the topic model. This work was supported in part by NSFC under Grant 61972106, Grant U1636215, Grant 61871140, Grant 61572153, and Grant 61872420, in part by the National Key research and Development Plan under Grant 2019QY1406 and Grant 2018YFB0803504, in part by the Guangdong Province Key Research and Development Plan under Grant 2019B010136003 and Grant 2019B010137004

The 5G network provides higher bandwidth and lower latency for edge IoT devices to access the core business network. But at the same time, it also expands the attack surface of the core network, which makes the enterprise network face greater security threats. To protect the security of core business, the network infrastructure must be able to recognize not only the known abnormal traffic, but also new emerging threats. Intrusion Detection Systems (IDSs) are widely used to protect the core network against external intrusions. Most of the existing research works design anomaly detection models for a specific set of traffic attributes. In fact, it is difficult for us to find the specific correspondence between traffic attributes and attack behaviors. Worse, some traffic attributes will be missing in the IoT environment, which further increases the difficulty of anomaly analysis. In traditional solutions, the missing attributes are usually filled with zero or mean values. Sometimes, the attributes are directly discarded. Both of these methods may result in lower detection accuracy. To solve this problem, we propose an intrusion detection method based on multiple-kernel clustering (MKC) algorithms. Be different from zero value filling and mean value filling, the proposed method completes the absent traffic property through similarity calculation. Experimental results show that this method can effectively improve the clustering accuracy of incomplete sampled data, at the same time it can reduce the sensitivity of the anomaly detection model to the selection of traffic feature, and has a better tolerance for poor-quality traffic sampled data.

Software-defined networks offer flexible and intelligent network operations by splitting a traditional network into a centralized control plane and a programmable data plane. The controller in the control plane is the fundamental element used to manage all operations of the data plane. Hence, the performance and capabilities of the controller itself are essential in achieving optimal performance. Furthermore, the tools used to benchmark their performance must be accurate and useful in measuring different evaluation parameters. There are dozens of controller proposals for general and specialized networks in the literature. However, there is a very limited comprehensive quantitative analysis for them. In this article, we present a comprehensive qualitative comparison of different SDN controllers, along with a quantitative analysis of their performance in different network scenarios. We categorize and classify 34 controllers and present a qualitative comparison. We also present a comparative analysis of controllers for specialized networks such as the Internet of Things, blockchain networks, vehicular networks, and wireless sensor networks. We also discuss in-depth capabilities of benchmarking tools and provide a comparative analysis of their capabilities. This work uses three benchmarking tools to compare 9 controllers and presents a detailed analysis of their performance, along with discussion on performance of specialized network controllers.

Fifth generation (5G) mobile systems are expected to be integrated with different radio access methods such as satellite components to provide seamless connectivity and ubiquitous coverage for users worldwide. In this article, we first provide a brief review of current initiatives and system architecture for the convergence of satellite and 5G networks. Then, we investigate various approaches to improve reliability or security at the physical layer for the integrated 5G-satellite networks. An effective achievable rate is presented as the key performance indicator to measure the security and reliability trade-off, followed by the implementation of a proposed beamforming scheme. Finally, we present future trends and challenges in integrated 5G-satellite networks. This work was supported in part by the Key International Cooperation Research Project under Grant 61720106003, and in part by the Shanghai Aerospace Science and Technology Innovation Foundation under Grant SAST2019-095.

With the rise of new technological paradigms such as the Internet of Things (IoT) and the Internet of Vehicles (IoV), we are going to see an unprecedented growth of connected vehicles on the roads. Also, with the ever-increasing complexity of vehicular electronics and with the increasing number of Electronic Control Units (ECUs) inside these next-generation vehicles, the need for verification of the firmware and software running on these ECUs using attestation techniques is heightened all the more. In this paper, we propose a lightweight and secure authentication and attestation scheme for attesting vehicles while they are on the roads. Since this attestation is proposed to be carried out on moving vehicles, there is also a need for authenticating the vehicles with the Road Side Units (RSUs) first before carrying out attestation. Therefore, a combined attestation and authentication scheme for verification of the vehicle ECU firmware is presented here. The ECU firmware running on the vehicles can be attested from the edge servers connected to the RSUs while the vehicles are in-transit and passing through these RSUs. We perform a security analysis of the proposed attestation and authentication protocol and compare it with other similar existing protocols. We also do a performance analysis of the proposed protocol and show the feasibility of its deployment. This work was partially supported in part by the SICI SICRG grant received by Dr. Vinay Chamola for the project Artificial Intelligence Enabled Security Provisioning and Vehicular Vision innovations for Autonomous Vehicles. The review of this article was coordinated by Prof. Liehuang Zhu. (Corresponding author: Mohsen Guizani.) Tejasvi Alladi and Sombuddha Chakravarty are with the Department of Electrical and Electronics Engineering, BITS-Pilani, Pilani 333031, India (e-mail: p20170433@pilani.bits-pilani.ac.in; f2016165@pilani.bits-pilani.ac.in).

Due to the bursty nature of Internet traffic, network service providers (NSPs) are forced to expand their network capacity in order to meet the ever-increasing peak-time traffic demand, which is however costly and inefficient. How to shift the traffic demand from peak time to off-peak time is a challenging task for NSPs. In this paper, we study the implementation of time-dependent pricing (TDP) for bandwidth slicing in software-defined cellular networks under information asymmetry and price discrimination. Congestion prices indicating real-time congestion levels of different links are used as a signal to motivate delay-tolerant users to defer their traffic demands. We formulate the joint pricing and bandwidth demand optimization problem as a two-stage Stackelberg leader-follower game. Then, we investigate how to derive the optimal solutions under the scenarios of both complete and incomplete information. We also extend the results from the simplified case of a single congested link to the more complicated case of multiple congested links, where price discrimination is employed to dynamically adjust the price of each congested link in accordance with its real-time congestion level. Simulation results demonstrate that the proposed pricing scheme achieves superior performance in increasing the NSP’s revenue and reducing the peak-to-average traffic ratio (PATR).

In this article, we propose a downlink non-orthogonal multiple access (NOMA) based coordinated direct and relay system with one cell-center user and multiple cell-edge users, where a decode-and-forward (DF) relay bridges the connection between the base station and the cell-edge users. Both full-duplex (FD) and half-duplex (HD) protocols are considered for the relay. We assume that the performance of the cell-edge users is subjected to the relay, and the cancellation of the mutual interference between the relay and cell-center user is imperfect. Both the exact analytical expression of outage probability and an approximate expression of the ergodic sum rate at high signal-to-noise ratio (SNR) are derived. Numerical results demonstrate that: 1) the FD relaying NOMA system outperforms the HD relaying NOMA system at low SNR, but the situation is exactly the opposite at high SNR; 2) the mutual interference can cause a larger performance gap than the self-interference at the relay; 3) the power allocation coefficients for the cell-center user and relay can affect the performance more significantly than those for cell-edge users.11This article was presented in part at the IEEE International Workshop on Signal Processing Advances in Wireless Communications 2019 [1]. This work was supported in part by the National Natural Science Foundation of China under Grant 61871190, U1809211, and 61771202, in part by the Natural Science Foundation of Guangdong Province under Grant 2018B030306005, in part by the Pearl River Nova Program of Guangzhou under Grant 201806010171

Opportunistic communications as an efficient traffic offloading method can be used to offload uplink traffic of cellular networks to Wi-Fi networks. However, because of its contact pattern (contact frequency and contact duration) the offloading method could not ensure the data to be successfully offloaded to Wi-Fi Access Points (APs) within a time constraint. In this paper, we focus on maximizing the probability of offloading data to Wi-Fi APs by fragmenting the data and assigning the fragments to different direct or indirect paths generated by opportunistic contacts. Firstly, we propose two methods based on mobility prediction, which is realized by machine learning, to separately calculate the probability of offloading data to Wi-Fi APs by the direct offloading path considering multiple opportunistic contacts and contact duration, and the probability of indirectly offloading data to Wi-Fi APs by the indirect offloading path. Then, based on the probability calculation methods the offloading probability maximization is formulated as a non-linear integer programming problem, and we propose a distributed heuristic algorithm to solve it considering complexity of the probability calculation and limited computation capacities of devices. Simulation results prove the data offloading probability of our proposed algorithm outperforms other algorithms under different simulation environment.

Information-Centric Networking (ICN) is a novel future network architecture which in contrast to IP-based networks relies on content and its name. It separates the physical location of data from the discovery and forwarding process and solely relies on the content itself. For the Internet of Thing (IoT) networks, stripping the location information may provide privacy, but this does not translate to operational privacy. Attackers can infer user behavior patterns through operational privacy, by eavesdropping on meaningful information. The content name and designed signature in ICN can associate content with the identity of the provider, even if the IP address is hidden. Although several research efforts focus on the privacy protection of ICN, they do not consider the privacy implications of data aggregation. Most existing privacy-preserving data aggregation protocols are designed for special operations, such as sum, average, variance, max or min, and they cannot support arbitrary aggregation operations in the ciphertexts domain. Besides, the need for trusted authority (TA) restricts the use of existing protocols in the real world. In this paper, we propose a practical and privacy-preserving data aggregation scheme that can compute arbitrary aggregation functions without a TA. On one hand, our scheme can ensure users’ anonymity and privacy protection, while on the other, the scheme is efficient in enabling participants to join or leave the system dynamically. Security analysis shows that the proposed scheme can achieve the desired security properties, while experimental results demonstrate its effectiveness and efficiency. This research is supported by the National Natural Science Foundation of China (Grant Nos. 61972037 , 61402037 , 61872041 , U1836212 ).

With the rapid development of the Internet, the nextgeneration network (5G) has emerged. 5G can support a variety of new applications, such as the Internet of Things (IoT), virtual reality (VR), and the Internet of Vehicles. Most of these new applications depend on deep learning algorithms, which have made great advances in many areas of artificial intelligence (AI). However, researchers have found that AI algorithms based on deep learning pose numerous security problems. For example, deep learning is susceptible to a well-designed input sample formed by adding small perturbations to the original sample. This well-designed input with small perturbations, which are imperceptible to humans, is called an adversarial example. An adversarial example is similar to a truth example, but it can render the deep learning model invalid. In this article, we generate adversarial examples for spatiotemporal data. Based on the travel time estimation (TTE) task, we use two methods-white-box and blackbox attacks-to invalidate deep learning models. Experiment results show that the adversarial examples successfully attack the deep learning model and thus that AI security is a big challenge of 5G. This research is supported by the Guangdong Province Key Research and Development Plan (grant 2019B010137004); National Key Research and Development Plan (grant 2018YFB0803504); National Natural Science Foundation of China (grants 61871140, 61872100, and U1636215)

Electric vehicles (EVs) have been slowly replacing conventional fuel based vehicles since the last decade. EVs are not only environment-friendly but when used in conjunction with a smart grid, also open up new possibilities and a Vehicle-Smart Grid ecosystem, commonly called V2G can be achieved. This would not only encourage people to switch to environment-friendly EVs or Plug-in Hybrid Electric Vehicles (PHEVs), but also positively aid in load management on the power grid, and present new economic benefits to all the entities involved in such an ecosystem. Nonetheless, privacy and security remain a serious concern of smart grids. The devices used in V2G are tiny, inexpensive, and resource constrained, which renders them susceptible to multiple attacks. Any protocol designed for V2G systems must be secure, lightweight, and must protect the privacy of the vehicle owner. Since EVs and charging stations are generally not guarded by people, physical security is also a must. To tackle these issues, we propose Physical Unclonable Functions (PUF) based Secure User Key-Exchange Authentication (SUKA) protocol for V2G systems. The proposed protocol uses PUFs to achieve a two-step mutual authentication between an EV and the Grid Server. It is lightweight, secure, and privacy preserving. Simulations show that the proposed protocol performs better and provides more security features than state-of-the-art V2G authentication protocols. The security of the proposed protocol is shown using a formal security model and analysis. This work was supported by the Singapore Ministry of Education Academic Research Fund Tier 1 (R-263-000-D62-114).

The prosperity of cloud computing has driven an increasing number of enterprises and organizations to store their data on private or public cloud platforms. Due to the limitation of individual data owners in terms of data volume and diversity, data sharing over different cloud platforms would enable third parties to take advantage of big data analysis techniques to provide value-added services, such as providing healthcare services for customers by gathering medical data from multiple hospitals. However, it remains a challenging task to design effective incentives that encourage secure and collaborative data sharing in multiple clouds. In this paper, we propose a reliable collaboration model consisting of three types of participants, which include data owners, miners, and third parties, where the data is shared via blockchain and recorded by a smart contract. In general, these participants may acquire and store the sharing of data using their private or public clouds. We analyze the topological relationships between the participants and develop some Shapley value models from simple to complicate in the process of revenue distribution. We also discuss the incentive effect of sharing security data and rationality of the designed solution through analysis towards distribution rules. This work is partially supported by the Beijing Natural Science Foundation under Grant 4192050, and in part by the National Natural Science Foundation of China under Grants 61972039 and 61872041.

The Aerial Internet-of-Things (Aerial-IoT) systems, deploying sensors on high-altitude platforms, e.g., drones, parachutes, and aircrafts, are a crucial monitor due to its agile maneuverability and augmentation of observation, collection, and communication. As such, the measurement accuracy and requirements of Aerial-IoT are far beyond the ability of general commercial-off-the-shelf sensors, especially in the high-altitude environment, where environmental factors (air pressure, temperature, humidity, wind movement, etc.) tend to change rapidly and lead to highly deviated readings. In this article, we tackle this challenge. First, we introduce our designed measurement system for Aerial-IoT. Then, to compensate for the low data quality and calibrate the deviation data from sensors, we take into account the inherent correlations and interaction between sensor data and environmental factors, and construct a data calibration model, called data calibration based on the neural network (DC-NN). Finally, to illustrate the effectiveness of our system, we carry out a real-world implementation by deploying sensors on the surface of parachutes in a dynamic airdrop environment. Extensive experiments on temperature-humidity-material-tensile-testing (THMTT) and high-altitude airdrop are conducted to show the significant improvements of our proposed DC-NN model.

This paper proposes cloudlet-based intelligent agents for energy crowdsourcing from autonomous electric vehicles (AEVs). Existing energy crowdsourcing mechanisms focus on load shedding and cost savings, but lack incentive models for strategically behaving agents. In the proposed model, crowdsourcing agents residing on the edge network communicate with AEVs to stimulate them to participate in providing energy to the grid during peak time periods. The focus of this paper is on the development of incentive mechanisms that allow the agents to engage in an auctioning process according to their energy contribution. Through theoretical analysis and simulations, we evaluate the performance of the proposed model with respect to individual rationality, computational efficiency, and truthfulness. This work was supported by the Deanship of Scientific Research at King Saud University, Riyadh, Saudi Arabia, through the Vice Deanship of Scientific Research Chairs: Chair of Smart Cities Technology.

The demand for content usage over the Internet has exponentially increased with the rise in social networking, messaging, and smart devices. The host-centric communication model was not primarily designed for content as its core element, rather it emphasis on the connection between hosts. Information-Centric Networking (ICN) is fast becoming an Internet architecture for content distribution. In ICN, content is located and retrieved dynamically from a source or a cache store, without any binding to the producer host machine. This ICN feature improves the network performances, however, it raises security concerns regarding user or consumer authorization and access control management for private contents. In addition, the privacy of data (and consumers) can be compromised since data are cached away from the producer. To overcome these security challenges, this work proposes a Time-based Content access control Mechanism for subscribed content (T-CAM), which allows access only to authorized subscribers. The scheme allows the content producers to encrypt the content using their unique identities and defined access-time. We utilize identity-based encryption, proxy re-encryption, and broadcast encryption to ensure content dissemination and access management is done securely and effectively. Experimental and comprehensive security evaluation proves the effectiveness and reliability of the scheme.

In the face of a massive number of vehicular users, a data collection paradigm based on vehicular crowdsensing requires an effective means of attracting participants. Thus, the incentive mechanisms play a key role in crowdsensing procedure design, inevitably leading to problems related to user privacy leakage. In this article, to reduce the risk of privacy leakage in the implementation of incentive mechanisms, we propose a fog computing-based crowdsensing architecture specialized for vehicular crowdsensing and corresponding privacy-preserving solutions for the processes of data reporting, reward issuing, and trust management. Authentication and encryption technologies, such as zero-knowledge verification, one-way hashing, partially blind signature authentication, and homomorphic encryption, are utilized to achieve our goals. Finally, efficiency improvements in both privacy preservation and network response are proven through analysis and simulations. This work was supported in part by the National Natural Science Foundation of China under Grant 61571098, in part by the Sichuan Science and Technology Program under Grant 2019YGF0206, and in part by the 111 Project under Grant B14039.

Industrial Internet of Things (IIoT) is considered as one of the most promising revolutionary technologies to prompt smart manufacturing and increase productivity. With manufacturing being more complicated and sophisticated, an entire manufacturing process usually involves several different administrative IoT domains (e.g., factories). Devices from different domains collaborate on the same task, which raises great security and privacy concerns about device-to-device communications. Existing authentication approaches may result in heavy key management overhead or rely on a trusted third party. Thus, security and privacy issues during communication remain unsolved but imperative. In this paper, we present an efficient blockchain-assisted secure device authentication mechanism $\textsf{BASA}$ for cross-domain IIoT. Specifically, consortium blockchain is introduced to construct trust among different domains. Identity-based signature (IBS) is exploited during the authentication process. To preserve the privacy of devices, we design an identity management mechanism, which can realize that devices being authenticated remain anonymous. Besides, session keys between two parties are negotiated, which can secure the subsequent communications. Extensive experiments have been conducted to show the effectiveness and efficiency of the proposed mechanism. This work was supported in part by the National Key Research and Development Program of China under Grant 2018YFB0803405, in part by the National Natural Science Foundation of China under Grant 61972039, Grant 61932016, and Grant 61872041, in part by the Beijing Natural Science Foundation under Grant 4192050, in part by China National Funds for Distinguished Young Scientists under Grant 61825204, in part by the Beijing Outstanding Young Scientist Program under Grant BJJWZYJH01201910003011, and in part by the Beijing National Research Center for Information Science and Technology (BNRist) under Grant BNR2019RC01011.

Radio access technologies, such as C-V2X and DSRC, have been used to support robust communication in connected vehicles scenarios. However, existing studies mostly dealt with homogenous vehicular networks, where coexistence of different radio access technologies in vehicles are not considered. More precisely, such multi-radio interface environments burden communications among vehicles. In this article, we first review DSRC and C-V2X radio access technologies and existing packet relaying mechanisms that are specifically designed for homogenous or heterogeneous vehicular environments. We then present a quality of service aware relaying algorithm (QR) that incorporates multi-metric to prioritize dual interface vehicles (DVs) and provides robust communications among vehicles that are equipped with different radio access technologies. The simulation results confirm the superiority of the proposed QR in terms of message reception and relaying count as compared to the standard protocols.

Artificial intelligence (AI)-driven fog computing (FC) and its emerging role in vehicular networks is playing a remarkable role in revolutionizing daily human lives. Fog radio access networks are accommodating billions of Internet of Things devices for real-time interactive applications at high reliability. One of the critical challenges in today's vehicular networks is the lack of standard wireless channel models with better quality of service (QoS) for passengers while enjoying pleasurable travel (i.e., highly visualized videos, images, news, phone calls to friends/relatives). To remedy these issues, this article contributes significantly in four ways. First, we develop a novel AI-based reliable and interference-free mobility management algorithm (RIMMA) for fog computing intra-vehicular networks, because traffic monitoring and driver's safety management are important and basic foundations. The proposed RIMMA in association with FC significantly improves computation, communication, cooperation, and storage space. Furthermore, its self-adaptive, reliable, intelligent, and mobility-aware nature, and sporadic contents are monitored effectively in highly mobile vehicles. Second, we propose a reliable and delay-tolerant wireless channel model with better QoS for passengers. Third, we propose a novel reliable and efficient multi-layer fog driven inter-vehicular framework. Fourth, we optimize QoS in terms of mobility, reliability, and packet loss ratio. Also, the proposed RIMMA is compared to an existing competitive conventional method (i.e., baseline). Experimental results reveal that the proposed RIMMA outperforms the traditional technique for intercity vehicular networks. This work is funded by CENIIT project 17.01, and a research grant of PIFI 2020 (2020VBC0002). This work was partially supported by NSERC Discovery and STPG Research funds, andNSERC CREATE-TRANSIT, and Canada Research Chairs Programs. This work is also supported by FCT project UID/EEA/50008/2019 (Este trabalho foi suportadopelo projecto FCT UID/EEA/50008/2019). This article/publication is based on work from COSTAction IC1303-AAPELE-Architectures, Algorithms and Protocols for Enhanced Living Environments and COST Action CA16226-SHELD-ON-Indoor living space improvement: Smart Habitat for the Elderly, supported by COST (European Cooperation in Science and Technology). This work was also partially supported by Operação Centro-010145-FEDER-000019–C4-Centro de Com-petências em Cloud Computing, co-financed by the Programa Operacional Regional do Centro (CENTRO 2020), through the Sistema de Apoio à Investigação Científica e Tecnológica — Pro-gramas Integrados de IC&DT.

Mobile crowdsensing (MCS) has been an emerging technology thanks to the smart devices which are capable of sensing and computing to achieve large-scale, complex sensing tasks by cooperation. However, large-scale deployment might be impeded due to that fact that the participant may face the risk of privacy leakage, and if they are not compensated favorably, they may not be willing to contribute sensing capability. To overcome the above challenges, we propose an incentive mechanism for privacy-preserving mobile crowdsensing. More specifically, we introduce a trusted third party and combine partially blind signature, which can effectively reduce the correlation between participants and data and the number of interactions between users and task platform, so as to achieve high level participant privacy. In addition, considering data quality, we define some concepts including data quality relevance, user credit, location relevance and user utility, and design a C redit-based I ncentive M echanism (CIM) based on marginal benefit density and credit, in order to obtain the maximum benefit of a task platform under given budget. Extensive simulations are carried out to show that the proposed incentive mechanism achieves superior performance compared with state-of-the-art solutions. To the existing multi-stage incentive solutions, our proposed solution can achieve higher-quality data at the expense of less time efficiency.

Data sharing and content offloading among vehicles is an imperative part of the Internet of Vehicles (IoV). A peer-to-peer connection among vehicles in a distributed manner is a highly promising solution for fast communication among vehicles. To ensure security and data tracking, existing studies use blockchain as a solution. The Blockchain-enabled Internet of Vehicles (BIoV) requires high computation power for the miners to mine the blocks and let the chain grow. Over and above, the blockchain consensus is probabilistic and the block generated today can be eventually declared as a fork and can be pruned from the chain. This reduces the overall efficiency of the protocol because the correct work done initially is eventually not used if it becomes a fork. To address these challenges, in this paper, we propose a Directed Acyclic Graph enabled IoV (DAGIoV) framework. We make use of a tangle data structure where each node acts as a miner and eventually the network achieves consensus among the nodes. A game-theoretic approach is used to model the interactions between the vehicles providing and consuming offloading services. The proposed model is proven to be highly scalable and well suited for microtransactions or frequent data transfer among the nodes in the vehicular network. This work was supported in part by the National Key Research and Development Program under Grant 2017YFE0125300, in part by the National Natural Science Foundation of China-Guangdong Joint Fund under Grant U1801264, in part by the JiangsuKey Research andDevelopment Program under Grant BE2019648, in part by FCT/MCTES through national funds and when applicable cofunded EU funds under Project UIDB/EEA/50008/2020, and in part by Brazilian NationalCouncil for Scientific andTechnologicalDevelopment (CNPq) under Grant 309335/2017-5.

These redundant data in IoT should be compressed or removed. Furthermore, the unstructured data in IoT plays an important role for analyzing the user behaviors, while transmitting and processing these unstructured data consumption of substantial energy. These unstructured data should be mined or restructured. In addition, the increasing number of users in IoT leads to a fast-growing data in IoT, while the Quality of Service (QoS) of IoT should be maintained regardless of the number of IoT users. Therefore, the data transmission and processing in IoT should be performed in a more intelligent manner. All these observations indicate that the integration of big data and artificial intelligence (AI) for IoT is a good propellant to improve the data transmission and processing in IoT, since big data technology (e.g., data integration, data mining, data prediction) could effectively handle various data while AI technology could further facilitate capturing and structuring big data.

Power allocation plays a vital role in coordinating interference between Device-to-Device (D2D) and cellular communications, and when power allocation meets simultaneous wireless information and power transfer (SWIPT), the energy efficiency of D2D communications can be significantly improved. While numerous research studies have been conducted on D2D power allocation, most of these studies do not take the presence of SWIPT into consideration. Toward a remedy for this issue, we investigate the problem of D2D power allocation with SWIPT power-splitting architecture, and address it by establishing a novel game-theoretic model. Two power allocation mechanisms are proposed to simultaneously allocate transmit power and choose power splitting ratio for D2D communications. We also develop two pricing strategies for the proposed power allocation mechanisms based on the social utility (sum utility of both D2D and cellular communications) maximization. Simulation results validate theoretical analyses and the effectiveness of the proposed mechanisms. In particular, we find through performance comparisons that our developed pricing strategies are light-weighted and energy-efficient, and the distributed power allocation mechanism is responsive to the mobility of D2D users. This work was supported by the Chongqing Key Laboratory of Computer Networking and Communications. The associate editor coordinating the review of this article and approving it for publication was M. Dong. (Corresponding author: Jun Huang.) Jun Huang is with the School of Computer Science, Chongqing University of Posts and Telecommunications, Chongqing 400065, China (e-mail: huangj@ieee.org).

Secure data aggregation has been widely studied in the area of smart grid. Many existing schemes have studied protecting user’s privacy in data aggregation by using advanced cryptographic tools. However, they usually introduce large computation burden to smart meters in limited computing power or require a trusted authority. How to ensure the efficiency on the user side while preserving user’s privacy still has not been well addressed. In this paper, we consider the scenario where there does not exist a trusted authority and users in the smart grid may dynamically change, and propose an efficient and robust data aggregation scheme without a trusted authority for the smart grid. Our proposed scheme not only ensures user’s privacy and efficiency, but also supports flexible dynamic user management with no need of involving a trusted authority. Analysis of security and performance shows that our scheme can guarantee stronger security features, while ensuring efficiency in terms of computation, communication, and storage overhead. IEEE Scopus

The ever-increasing urban population and the corresponding material demands have brought unprecedented burdens to cities. To guarantee better QoS for citizens, smart cities leverage emerging technologies such as the Cognitive Radio Internet of Things (CR-IoT). However, resource allocation is a great challenge for CR-IoT, mainly because of the extremely numerous devices and users. Generally, the auction theory and game theory are applied to overcome the challenge. In this paper, we propose a multi-agent reinforcement learning (MARL) algorithm to learn the optimal resource allocation strategy in the oligopoly market model. Firstly, we model a multi-agent scenario with the primary users (PUs) as sellers and secondary users (SUs) as buyers. Then, we propose the Q-probabilistic multi-agent learning (QPML) and apply it to allocate resources in the market. In the multi-agent learning process, the PUs and SUs learn strategies to maximize their benefits and improve spectrum utilization. The performance of QPML is compared with Learning Automation (LA) through simulations. The experimental results show that our approach outperforms other approaches and performs well. IEEE Scopus

Due to the unavailability of Vehicle-to-Infrastructure (V2I) communication in current transportation systems, Traffic Light Detection (TLD) is still considered an important module in autonomous vehicles and Driver Assistance Systems (DAS). To overcome low flexibility and accuracy of vision-based heuristic algorithms and high power consumption of deep learning-based methods, we propose a lightweight and real-time traffic light detector for the autonomous vehicle platform. Our model consists of a heuristic candidate region selection module to identify all possible traffic lights, and a lightweight Convolution Neural Network (CNN) classifier to classify the results obtained. Offline simulations on the GPU server with the collected dataset and several public datasets show that our model achieves higher average accuracy and less time consumption. By integrating our detector module on NVidia Jetson TX1/TX2, we conduct on-road tests on two full-scale self-driving vehicle platforms (a car and a bus) in normal traffic conditions. Our model can achieve an average detection accuracy of 99.3 percent (mRttld) and 99.7 percent (Rttld) at 10Hz on TX1 and TX2, respectively. The on-road tests also show that our traffic light detection module can achieve

The papers in this special section examine artificial intelligence (AI)-driven developments in 5G mobile communications for industrial automation applications from a Big Data perspective. With the recent advances in information and communication technologies, industrial automation is expanding at a rapid pace. This transition is characterized by “Industry 4.0”, the fourth revolution in the field of manufacturing. Industry 4.0, also called as “Industrial Internet of Things (IIoT)” or “Smart Factories”, is a reflection of new industrial revolution that is not only interconnected, but also communicate, analyze, and use the information to create a more holistic and better connected ecosystem for the industries.

5G wireless network technology will not only significantly increase bandwidth but also introduce new features such as mMTC and URLLC. However, high request latency will remain a challenging problem even with 5G due to the massive requests generated by an increasing number of devices that require long travel distances to the services deployed in cloud centers. By pushing the services closer to the edge of the network, edge computing is recognized as a promising technology to reduce latency. However, properly deploying services among resource-constrained edge servers is an unsolved problem. In this article, we propose a deep reinforcement learning approach to preferably deploy the services to the edge servers with consideration of the request patterns and resource constraints of users, which have not been adequately explored. First, the system model and optimization objectives are formulated and investigated. Then the problem is modeled as a Markov decision process and solved using the Dueling-Deep Q-network algorithm. The experimental results, based on the evaluation of real-life mobile wireless datasets, show that this reinforcement learning approach could be applied to patterns of requests and improve performance. This work is supported by the National Nature Science Foundation of China (Grant No. 61602037) and the Equipment Pre-Research Field Foundation (Grant No. 61400010104).

The electromagnetic radiation (EMR) emitted out of wireless communication modules in various IoT devices (especially used for healthcare applications due to their close proximity to the body) have been identified by researchers as biologically hazardous to humans as well as other living beings. Different countries have different regulations to limit the radiation density levels caused by these devices. The radiation absorbed by an individual depends on various factors such as the device they use, the proximity of use, the type of antenna, the relative orientation of the antenna on the device, and many more. Several standards exist which have tried to quantify the radiation levels and come up with safe limits of EMR absorption to prevent human harm. In this work, we determine the radiation concern levels in several scenarios using a handheld radiation meter by correlating the findings with several international standards, which are determined based on thorough scientific evidence. This study also analyzes the EMR from common devices used in day to day life such as smartphones, laptops, Wi-Fi routers, hotspots, wireless earphones, smartwatches, Bluetooth speakers and other wireless accessories using a handheld radio frequency radiation measurement device. The procedure followed in this paper is so detailed that it can also be utilized by the general public as a tutorial to evaluate their own safety with respect to EMR exposure. We present a summary of the most prominent health hazards which have been known to occur due to EMR exposure. We also discuss some individual and collective human-centric protective and preventive measures that can be undertaken to reduce the risk of EMR absorption. This paper analyses radiation safety in pre-5G networks and uses the insight gained to raise valuable concerns regarding EMR safety in the upcoming 5G networks.

The Internet of Things (IoT) integrates billions of smart devices that can communicate with one another with minimal human intervention. IoT is one of the fastest developing fields in the history of computing, with an estimated 50 billion devices by the end of 2020. However, the crosscutting nature of IoT systems and the multidisciplinary components involved in the deployment of such systems have introduced new security challenges. Implementing security measures, such as encryption, authentication, access control, network and application security for IoT devices and their inherent vulnerabilities is ineffective. Therefore, existing security methods should be enhanced to effectively secure the IoT ecosystem. Machine learning and deep learning (ML/DL) have advanced considerably over the last few years, and machine intelligence has transitioned from laboratory novelty to practical machinery in several important applications. Consequently, ML/DL methods are important in transforming the security of IoT systems from merely facilitating secure communication between devices to security-based intelligence systems. The goal of this work is to provide a comprehensive survey of ML methods and recent advances in DL methods that can be used to develop enhanced security methods for IoT systems. IoT security threats that are related to inherent or newly introduced threats are presented, and various potential IoT system attack surfaces and the possible threats related to each surface are discussed. We then thoroughly review ML/DL methods for IoT security and present the opportunities, advantages and shortcomings of each method. We discuss the opportunities and challenges involved in applying ML/DL to IoT security. These opportunities and challenges can serve as potential future research directions. 1998-2012 IEEE. Qatar Foundation;Qatar National Research Fund Scopus

Recently, research intergrading medicine and Artificial Intelligence has attracted extensive attention. Mobile health has emerged as a promising paradigm for improving people's work and life in the future. However, high mobility of mobile devices and limited resources pose challenges for users to deal with the applications in mobile health that require large amount of computational resources. In this paper, a novel computation offloading mechanism is proposed in the environments combining of the Internet of Vehicles and Multi-Access Edge Computing. Through the proposed mechanism, mobile health applications are divided into several parts and can be offloaded to appropriate nearby vehicles while meeting the requirements of application completion time, energy consumption, and resource utilization. A particle swarm optimization based approach is proposed to optimize the the aforementioned computation offloading problem in a specific medical application. Evaluations of the proposed algorithms against local computing method serves as baseline method are conducted via extensive simulations. The average task completion time saved by our proposed task allocation scheme increases continually compared with the local solution. Specially, the global resource utilization rate increased from 71.8% to 94.5% compared with the local execution time.